Context-aware Attention Network for Predicting Image Aesthetic Subjectivity
| Autor: | Munan Xu, Jia-Xing Zhong, Shan Liu, Ge Li, Yurui Ren |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Subjectivity
Spatial contextual awareness Information retrieval Computer science business.industry media_common.quotation_subject Deep learning 020206 networking & telecommunications Context (language use) 02 engineering and technology Binary classification Perception Similarity (psychology) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence business Diversity (politics) media_common |
| Zdroj: | ACM Multimedia |
| DOI: | 10.1145/3394171.3413834 |
| Popis: | Image aesthetic assessment involves both fine-grained details and the holistic layout of images. However, most of current approaches learn the local and the holistic information separately, which has a potential loss of contextual information. Additionally, learning-based methods mainly cast image aesthetic assessment as a binary classification or a regression problem, which cannot sufficiently delineate the potential diversity of human aesthetic experience. To address these limitations, we attempt to render the contextual information and model the varieties of aesthetic experience. Specifically, we explore a context-aware attention module in two dimensions: hierarchical and spatial. The hierarchical context is introduced to present the concern of multi-level aesthetic details while the spatial context is served to yield the long-range perception of images. Based on the attention model, we predict the distribution of human aesthetic ratings of images, which reflects the diversity and similarity of human subjective opinions. We conduct extensive experiments on the prevailing AVA dataset to validate the effectiveness of our approach. Experimental results demonstrate that our approach achieves state-of-the-art results. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|